JP7068781B2 - Harvester - Google Patents

Description

The present invention relates to a harvester capable of harvesting agricultural products while traveling in a field and supporting harvesting work based on a photographed image acquired by a photographing unit.

When harvesting crops using a field harvester, attention must be paid to the growing conditions of locally different crops and the presence of obstacles, including people. For this reason, for example, the combine according to Patent Document 1 is provided with a television camera and an image processing device for photographing the grain culm in front of the cutting section. The image processing apparatus detects a specific state of the grain culm by comparing the image from the television camera with the image showing the planting state of various grain culms stored in advance. For example, when the image processing device detects that a part of the grain culm in front of the cutting portion is laid down, the scraping reel is tilted with the culm culm side facing down. This improves the cutting performance of the fallen grain culm. Further, in the combine according to Patent Document 2 provided with a television camera and an image processing device as in the combine of Patent Document 1, when it is detected that there is no grain in front of the harvesting portion, the combine is used as a headland. The power transmission to the cutter is cut off, the cutter is raised, and the traveling speed is reduced. As a result, the collision with the ridges of the cutter during the rotation of the headland is avoided, and the combine headland is smoothly rotated.

Japanese Unexamined Patent Publication No. 11-155340 Japanese Unexamined Patent Publication No. 11-137062

In the combine according to Patent Document 1 and Patent Document 2, the state of the grain culm in front of the cutting section is detected by using an image processing technique, and the operation of the working equipment is controlled based on the detection result. However, the actual location on the map in the field of the detected culm is not taken into account. For this reason, even if a grain culm in a problematic state during work running is detected and avoidance control is performed to solve the problem, the area showing the problematic grain culm state and the combine are far apart. In some cases, the problem of avoidance control being too early or too late arises. In addition, it is difficult to appropriately determine the timing at which the avoidance control should be terminated.

In view of the above-mentioned circumstances, there is a demand for a harvesting machine that effectively supports harvesting work using images taken by a photographing unit provided on the vehicle body.

The first feature of the present invention is a harvester that harvests agricultural products while traveling in a field, and has an aircraft position calculation unit that calculates an aircraft position that is map coordinates of the aircraft based on positioning data from a satellite positioning module. , An image data of a photographing unit provided on the machine body and photographing a field at the time of harvesting work and an image data of photographed images sequentially acquired by the photographing unit are input, and a recognition target in the photographed image exists. An image recognition module that estimates an existing area and outputs recognition output data including an estimated probability when the existing area and the existing area are estimated, and the machine position and the recognition output at the time when the captured image is acquired. It is provided with a recognition target position information generation unit that generates recognition target position information indicating the position of the recognition target on a map from the data.
In the photographed image, the farther the recognition object is from the imaged portion, the lower the estimation probability of the recognition object is.
The second feature of the present invention is a harvester that harvests agricultural products while traveling in a field, and has an aircraft position calculation unit that calculates an aircraft position that is map coordinates of the aircraft based on positioning data from a satellite positioning module. , An image data of a photographing unit provided on the machine body and photographing a field at the time of harvesting work and an image data of photographed images sequentially acquired by the photographing unit are input, and a recognition target in the photographed image exists. An image recognition module that estimates an existing area and outputs recognition output data including an estimated probability when the existing area and the existing area are estimated, and the machine position and the recognition output at the time when the captured image is acquired. It is provided with a recognition target position information generation unit that generates recognition target position information indicating the position of the recognition target on a map from the data.
A plurality of the recognized object position information is stored, and the stored plurality of the recognized object position information is corrected based on the result of the statistical calculation of the estimated probability included in the corresponding recognition output data. There is a point.
The third feature of the present invention is a harvester that harvests agricultural products while traveling in a field, and has an aircraft position calculation unit that calculates an aircraft position that is map coordinates of the aircraft based on positioning data from a satellite positioning module. , An image data of a photographing unit provided on the machine body and photographing a field at the time of harvesting work and an image data of photographed images sequentially acquired by the photographing unit are input, and a recognition target in the photographed image exists. An image recognition module that estimates an existing area and outputs recognition output data including an estimated probability when the existing area and the existing area are estimated, and the machine position and the recognition output at the time when the captured image is acquired. It is provided with a recognition target position information generation unit that generates recognition target position information indicating the position of the recognition target on a map from the data.
A data storage unit that temporarily and temporally stores the recognition output data sequentially output from the image recognition module as a recognition output data string, and a data determination unit are provided.
The data determination unit inappropriately recognizes and outputs the recognition output data having the estimation probability lower than a predetermined level as compared with the estimation probability of the recognition output data which has a temporal relationship in the recognition output data string. The point is to judge as data.

In the present invention, the image recognition module that estimates the existence region where the recognition target exists in the captured image from the image data that is the captured image uses, for example, a technique such as a neural network (including deep learning) or reinforcement learning. It is configured. Further, since the estimated probability when the existing region is estimated can be output at the same time, the optimum control using the probability value is also possible. Furthermore, the aircraft position indicated by the map coordinates at the time when the captured image is acquired is calculated by the aircraft position calculation unit, and is recognized from the aircraft position and the recognition output data indicating the area where the recognition target is present. Recognized object position information indicating the position of the object on the map is generated. From such a configuration, the harvesting work support considering the estimated probability of estimating the existence area of the perceptible object, the position on the map of the perceptible object, and as a result, the distance between the perceptible object and the harvester. Can be controlled.

In the captured image of the field photographed by the photographing unit, the resolution for the perceptible object far from the photographing unit is lower than the resolution for the perceptible object near the photographing unit due to the perspective method. For this reason, the recognition object that is photographed at a place far from the photographing unit has lower recognition reliability than the recognition object that is photographed at a place close to the photographing unit. Therefore, in the first feature of the present invention, the estimation probability of the perceptible object is reduced as the recognition object is located farther from the imaging unit in the photographed image. ..

Since the generation of the perceptible object position information based on the captured image can be performed at a higher speed than the vehicle speed of the harvester, a plurality of perceptible object position information relating to the same perceptible object is generated. Therefore, it is possible to statistically calculate each estimated probability included in a plurality of recognition object position information regarding the same recognition object. Through this statistical calculation, more reliable recognition object position information can be generated. The statistical operation here is an arithmetic mean, a weight average, an intermediate value operation, or the like, and is an operation in which a more reliable data value is derived from a plurality of data values. By using such a statistical calculation for the estimation probability, it is possible to derive more appropriate recognition object position information from a plurality of recognition object position information. Therefore, in the second feature of the present invention, a plurality of the recognition target position information is stored, and the stored plurality of recognition target position information is included in the corresponding recognition output data. It is configured to be corrected based on the result of a statistical calculation of the estimated probability.

Although the captured image acquired by the photographing unit provided on the machine body is an input source of the image recognition module, it may be unsuitable for recognizing the recognition target depending on the photographing conditions. As a result, even if the recognition object is recognized, the recognition probability of the recognition output data is low, so it is not preferable to use the recognition output data as it is for the subsequent processing. Therefore, in the third feature of the present invention, a data storage unit that temporarily and temporally stores the recognition output data sequentially output from the image recognition module as a recognition output data string, and a data determination unit. The data determination unit is provided with the recognition output data having the estimation probability lower than a predetermined level as compared with the estimation probability of the recognition output data which has a temporal relationship in the recognition output data string. Is determined as inappropriate recognition output data. The recognition output data determined to be inappropriate recognition output data may be deleted, or the estimation probability of the recognition output data may be replaced with the estimation probability interpolated by the recognition output data before and after.

Perceptible objects that are important for harvesters who harvest crops while traveling in the field are people, fallen culms, weeds, and ridges. Recognizing a person who becomes an obstacle in work driving is important for safe driving in the field because it triggers obstacle avoidance control and obstacle warning notification. Recognizing the fallen culm and weeds is important for high-quality harvesting work because it serves as a control for the fallen culm and weeds in the work control. Recognizing the ridges will detect the boundary line of the field, which is important for controlling the running of the headland in the field.

It is an overall side view of a combine. It is a functional block diagram which shows the control system of a combine. It is explanatory drawing which shows typically the flow of the generation of recognition output data by an image recognition module. It is a data flow chart which shows the flow of data at the time of generating the recognition object position information from a captured image. It is a schematic diagram which shows the weed map obtained by mapping the weed position information as one of the recognition object position information.

Hereinafter, an embodiment of the combine as an example of the harvester according to the present invention will be described with reference to the drawings. In this embodiment, when the front-rear direction of the machine 1 is defined, it is defined along the traveling direction of the machine in the working state. The direction indicated by the reference numeral (F) in FIG. 1 is the front side of the aircraft, and the direction indicated by the reference numeral (B) in FIG. 1 is the rear side of the aircraft. When defining the left-right direction of the aircraft 1, the left-right direction is defined as viewed from the direction of travel of the aircraft.

As shown in FIG. 1, in the combine, the cutting section 2 is connected to the front portion of the machine body 1 provided with the pair of left and right crawler traveling devices 10 so as to be freely raised and lowered around the horizontal axis X. The rear part of the machine body 1 is provided with a threshing device 11 in a state of being lined up in the horizontal direction of the machine body, and a grain tank 12 for storing grains. A cabin 14 that covers the boarding operation unit is provided on the right side of the front portion of the aircraft 1, and a driving engine 15 is provided below the cabin 14.

As shown in FIG. 1, the threshing device 11 receives the harvested culm cut by the cutting unit 2 and transported to the rear inside, and the threshing feed chain 111 and the holding rail 112 are used to transfer the stock of the culm to the inside. While sandwiching and transporting, the tip side is handled and threshed by the barrel 113. Then, a grain sorting process for the threshed product is executed in the sorting section provided below the handling cylinder 113, and the sorted grains are transported to the grain tank 12 and stored. Further, although not described in detail, a grain discharge device 13 for discharging grains stored in the grain tank 12 to the outside is provided.

The cutting unit 2 is provided with a plurality of raising devices 21 that cause a fallen planted culm, a clipper-type cutting device 22 that cuts the root of the raised planted culm, a grain culm transport device 23, and the like. There is. The grain culm transport device 23 gradually changes the cut grain culm in the vertical position from which the stock root has been cut to the sideways position, toward the starting end of the threshing feed chain 111 of the threshing device 11 located on the rear side of the machine body. Transport.

The grain culm transport device 23 sandwiches and rearward a confluence transport section 231 that transports a plurality of cut grain culms cut by the cutting device 22 while gathering them in the center in the cutting width direction, and a stock base of the gathered cut grain culms. From the end of the stock root holding and transporting device 232, the tip locking transporting device 233 that locks and transports the tip side of the harvested culm, and the stock root holding and transporting device 232, the stock of the harvested culm is transferred to the grain removal feed chain 111. It is equipped with a supply / transport device 234 and the like to guide the culm.

A shooting unit 70 equipped with a color camera is provided at the front end of the ceiling portion of the cabin 14.
In this embodiment, the expansion of the photographing field of view of the photographing unit 70 in the front-rear direction reaches substantially the horizon from the front end region of the cutting unit 2. The width of the shooting field of view has expanded from about 10 m to several tens of meters. The captured image acquired by the photographing unit 70 is converted into image data and sent to the control system of the combine.

The photographing unit 70 photographs the field at the time of harvesting work, and various objects exist as objects to be photographed in the field. The combine control system has a function of recognizing a specific object as a recognition target from the image data sent from the photographing unit 70. As such recognition objects, in FIG. 1, the normal planted culm group indicated by the symbol Z0, the weed group extending higher than the planted culm indicated by the symbol Z1, and the lodging indicated by the symbol Z2. The culm group, the person indicated by reference numeral Z3, is schematically shown.

A satellite positioning module 80 is also provided on the ceiling of the cabin 14. The satellite positioning module 80 includes a satellite antenna for receiving GNSS (global navigation satellite system) signals (including GPS signals). In order to complement the satellite navigation by the satellite positioning module 80, an inertial navigation unit incorporating a gyro acceleration sensor and a magnetic orientation sensor is incorporated in the satellite positioning module 80. Of course, the inertial navigation unit can be placed elsewhere. In FIG. 1, the satellite positioning module 80 is arranged at the rear part of the ceiling part of the cabin 14 for convenience of drawing. It is preferable that it is arranged at a position closer to the center side of the aircraft at the front end portion.

FIG. 2 shows a functional block diagram of the combine control system. The control system of this embodiment is composed of a large number of electronic control units called ECUs, various operating devices, sensor groups and switch groups, and a wiring network such as an in-vehicle LAN that transmits data between them. The notification device 91 is a device for notifying a driver or the like of a work running state and various warnings, and is a buzzer, a lamp, a speaker, a display, and the like. The communication unit 92 is used for the control system of the combine to exchange data with the cloud computer system 100 and the mobile communication terminal 200 installed in a remote place. Here, the mobile communication terminal 200 is a tablet computer operated by a monitor (including a driver) at a work traveling site.
The control unit 6 is a core element of this control system and is shown as an aggregate of a plurality of ECUs. The positioning data from the satellite positioning module 80 and the image data from the photographing unit 70 are input to the control unit 6 through the wiring network.

The control unit 6 includes an output processing unit 6B and an input processing unit 6A as input / output interfaces. The output processing unit 6B is connected to the vehicle traveling equipment group 7A and the working equipment group 7B. The vehicle traveling device group 7A includes control devices related to vehicle traveling, such as an engine control device, a shift control device, a braking control device, and a steering control device. The working equipment group 7B includes a cutting unit 2, a threshing device 11, a grain discharging device 13, a power control device in the grain culm transport device 23, and the like.

A traveling system detection sensor group 8A, a working system detection sensor group 8B, and the like are connected to the input processing unit 6A. The traveling system detection sensor group 8A includes a sensor that detects the state of the engine speed adjusting tool, the accelerator pedal, the brake pedal, the speed change operating tool, and the like. The working system detection sensor group 8B includes a sensor for detecting the device state in the cutting unit 2, the threshing device 11, the grain discharging device 13, the grain culm transport device 23, and the state of the grain culm and the grain.

The control unit 6 includes a work travel control module 60, an image recognition module 5, a data processing module 50, an aircraft position calculation unit 66, and a notification unit 67.

The notification unit 67 generates notification data based on a command or the like from each functional unit of the control unit 6 and gives the notification data to the notification device 91. The aircraft position calculation unit 66 calculates the aircraft position, which is the map coordinates (or field coordinates) of the aircraft 1, based on the positioning data sequentially sent from the satellite positioning module 80.

The combine of this embodiment can travel in both automatic driving (automatic steering) and manual driving (manual steering). The work travel control module 60 is provided with an automatic work travel command unit 63 and a travel route setting unit 64 in addition to the travel control unit 61 and the work control unit 62. A traveling mode switch (not shown) for selecting between an automatic traveling mode for traveling by automatic steering and a manual steering mode for traveling by manual steering is provided in the cabin 14. By operating this travel mode switch, it is possible to shift from manual steering running to automatic steering running, or from automatic steering running to manual steering running.

The travel control unit 61 has an engine control function, a steering control function, a vehicle speed control function, and the like, and gives a travel control signal to the vehicle travel equipment group 7A. The work control unit 62 gives a work control signal to the work equipment group 7B in order to control the movements of the cutting unit 2, the threshing device 11, the grain discharge device 13, the grain culm transport device 23, and the like.

When the manual steering mode is selected, the travel control unit 61 generates a control signal and controls the vehicle travel equipment group 7A based on the operation by the driver. When the automatic steering mode is selected, the travel control unit 61 controls the vehicle travel equipment group 7A related to steering and the vehicle travel equipment group 7A related to vehicle speed based on the automatic travel command given by the automatic work travel command unit 63. ..

The travel route setting unit 64 expands the travel route for automatic travel created by any one of the control unit 6, the mobile communication terminal 200, the cloud computer system 100, etc. into the memory. The travel route expanded in the memory is used as a target travel route in sequential automatic travel. This travel route can be used for guidance for the combine to travel along the travel route even in manual travel.

More specifically, the automatic work travel command unit 63 generates an automatic steering command and a vehicle speed command and gives them to the travel control unit 61. The automatic steering command is generated so as to eliminate the directional deviation and the positional deviation between the traveling route and the own vehicle position calculated by the aircraft position calculation unit 66 by the traveling route setting unit 64. The vehicle speed command is generated based on a preset vehicle speed value. Further, the automatic work travel command unit 63 gives a work device operation command to the work control unit 62 according to the position of the own vehicle and the travel state of the own vehicle.

Image data of captured images sequentially acquired by the photographing unit 70 is input to the image recognition module 5. The image recognition module 5 estimates the existence region in which the recognition target exists in the captured image, and outputs the recognition output data including the existence region and the estimation probability when the existence region is estimated as the recognition result. The image recognition module 5 is constructed by using a neural network technique that employs deep learning.

The flow of generating the recognition output data by the image recognition module 5 is shown in FIGS. 3 and 4. The pixel value of the RGB image data is input to the image recognition module 5 as an input value. In the example of FIG. 3, the presumed objects to be certified are weeds, fallen culms and people. Therefore, in the recognition output data as the recognition result, the existence region of the weed (hereinafter referred to as the weed region) and its estimated probability, the existence region of the lodging grain (hereinafter referred to as the lodging grain region) and its estimated probability, The area where the person exists (hereinafter referred to as the person area) and its estimated probability are included.

In FIG. 3, the estimation results are schematically shown, the weed area is shown by a rectangular frame with the symbol F1, the fallen culm area is shown by the rectangular frame with the code F2, and the person area is shown. It is shown by a rectangular frame with the reference numeral F3. The estimated probabilities are linked to each region. The weed area, the fallen culm area, and the person area are each defined by four corner points, and the coordinate positions of the four corner points of each rectangle on the captured image are also included in the estimation result. Of course, if the authentication target is not estimated, the area where the authentication target exists is not output, and the estimation probability is zero.

In this embodiment, the image recognition module 5 sets an internal parameter so that the estimation probability of the recognition target is reduced as the recognition target is located farther from the shooting unit 70 in the captured image. .. As a result, the recognition of the perceptible object in the photographing region where the resolution is low because it is far away from the photographing unit 70 is strict, and the erroneous recognition is reduced.

The data processing module 50 processes the recognition output data output from the image recognition module 5. As shown in FIGS. 2 and 4, the data processing module 50 of this embodiment includes a recognition object position information generation unit 51, a statistical processing unit 52, a data storage unit 53, a data determination unit 54, and a data correction unit 55. include.

The recognition target position information generation unit 51 generates recognition target position information indicating the position of the recognition target on the map from the aircraft position at the time when the captured image is acquired and the recognition output data. The position on the map where the recognition object (weed, fallen grain image, person) included in the recognition output data exists is a rectangle indicating the existence area (weed area, fallen grain image area, person area) of the authentication target object. It is obtained by converting the coordinate positions (camera coordinate positions) on the captured image of the four corner points into the coordinates on the map.

Since the photographing unit 70 acquires captured images at predetermined time intervals, for example, 0.5 second intervals, and inputs the image data to the image recognition module 5, the image recognition module 5 also outputs recognition output data at the same time intervals. Output. Therefore, when the recognition target is included in the shooting field of view of the shooting unit 70, the plurality of recognition output data include the existence region for the same recognition target. As a result, a plurality of recognition target position information for the same recognition target can be obtained. At that time, the estimated probability included in the recognition output data which is each original data, that is, the estimated probability of the existence area of the recognized object included in the recognized object position information is determined between the photographing unit 70 and the recognized object. Since the positional relationship is different, the values are often different.

Therefore, in this embodiment, such a plurality of recognized object position information is stored, and the estimated probability included in each of the stored plurality of recognized object position information is statistically calculated.
The statistical processing unit 52 obtains a representative value of the estimated probability group by using a statistical calculation for the estimated probabilities of a plurality of recognition object position information. Using the representative value, a plurality of recognition object position information can be corrected to one optimum recognition object position information (recognition target correction position information). An example of such a correction is to obtain the arithmetic mean value, weighted mean value, or median value of each estimated probability as a reference value (representative value), and obtain the logical sum of existing regions having an estimated probability equal to or higher than the reference value. Is to generate the correction recognition target position information with the optimum existence area. Of course, it is also possible to generate one highly reliable perceptible object position information by using other statistical operations. That is, the plurality of recognition target position information is corrected based on the result of the statistical calculation of the estimated probability included in the recognition output data corresponding to the recognition target position information.

Recognition object position information (weed position information, fallen culm position information, person position) indicating the position on the map of the existence area (weed area, fallen culm area, person area) of the authentication target obtained in this way. Information) is used to perform preset running work control and warning notification when recognizing weeds, fallen culms, and people.

As described above, in the present invention, the estimated probability output from the image recognition module 5 is important for the generation of the final recognition target position information. Therefore, in this embodiment, the recognition output data evaluation that examines the reliability of the estimation probability of the recognition output data output from the image recognition module 5 and determines that the recognition output data having an unreliable estimation probability is inappropriate recognition output data. The function is provided in the data processing module 50.

As shown in FIGS. 2 and 4, the recognition output data evaluation function is realized by the data storage unit 53, the data determination unit 54, and the data correction unit 55. The data storage unit 53 temporarily and temporally stores the recognition output data sequentially output from the image recognition module 5 as a recognition output data string. The data determination unit 54 determines in the recognition output data string by comparing the estimation probability of the recognition output data to be determined with the estimation probability of the recognition output data which has a temporal relationship with the recognition output data. Recognition output data having an estimation probability lower than the level is judged as inappropriate recognition output data.

Since the captured image as a recognition source is captured during the work running of the combine, the captured image may become unclear due to sudden movement of the combine or the like. Furthermore, since the combine changes direction near the ridge, the shooting direction may change suddenly. Along with this, shooting in front light and shooting in backlight may be mixed with respect to the same recognition object. Recognition output data having an unexpectedly low estimation probability may be generated due to such fluctuations in shooting conditions, etc., but the extraction of inappropriate recognition output data, which is such recognition output data, is performed by the recognition output data evaluation function described above. It is possible.

When the number of recognition output data is small, the estimation probability of the recognition output data determined to be inappropriate recognition output data may be interpolated and corrected by the estimation probability of the recognition output data before and after that. As a result, the inappropriate recognition output data is appropriately corrected and can be used, and there is an advantage that the number of data is secured. The data correction unit 55 performs such interpolation correction. Of course, when discarding the recognition output data determined to be inappropriate recognition output data, interpolation correction becomes unnecessary, so the data correction unit 55 is omitted.

The position information of each recognition object generated by the recognition object position information generation unit 51 can be mapped as shown in FIG. 5 for visually easy-to-understand display. FIG. 5 illustrates a weed map in which weed position information is mapped. When the weed position information includes a weed existence area having a different estimated probability, it is also possible to display the weed existence area in a pattern-divided form within a predetermined range of the estimated probability value as shown in FIG. ..

The configuration disclosed in the above embodiment (including another embodiment, the same shall apply hereinafter) can be applied in combination with the configuration disclosed in other embodiments as long as there is no contradiction. The embodiments disclosed in the present specification are examples, and the embodiments of the present invention are not limited thereto, and can be appropriately modified without departing from the object of the present invention.

[Another embodiment]
(1) In the above-described embodiment, the image recognition module 5 is constructed by using a deep learning type neural network technique. Instead of this, an image recognition module 5 constructed by using other machine learning techniques may be adopted.
(2) In the above-described embodiment, the image recognition module 5 and the data processing module 50 are incorporated in the combine control unit 6, but a part or all of them are a control unit independent of the combine, for example, mobile communication. It can be built on a terminal 200 or the like.
(3) Each functional unit shown in FIG. 2 is divided mainly for the purpose of explanation. In practice, each functional unit may be integrated with other functional units, or may be further divided into a plurality of functional units.

According to the present invention, if the harvester has a function of photographing a field and a function of calculating the position of the machine, not only a combine for harvesting rice, wheat, etc., but also a combine for harvesting other agricultural products such as corn, a carrot, etc. It can also be applied to harvesters that harvest wheat.

1: Machine 2: Cutting unit 5: Image recognition module 50: Data processing module 51: Recognition target position information generation unit 52: Statistical processing unit 53: Data storage unit 54: Data determination unit 55: Data correction unit 6: Control unit 60: Work travel control module 61: Travel control unit 62: Work control unit 66: Aircraft position calculation unit 70: Imaging unit 80: Satellite positioning module

Claims (4)

It is a harvester that harvests crops while traveling in the field.
An aircraft position calculation unit that calculates the aircraft position, which is the map coordinates of the aircraft, based on the positioning data from the satellite positioning module.
A photography unit provided on the aircraft to photograph the field during harvesting work,
When the image data of the photographed images sequentially acquired by the photographing unit is input, the existence area where the recognition object exists in the photographed image is estimated, and the existence area and the existence area are estimated. An image recognition module that outputs recognition output data including the estimated probability of
A recognition target position information generation unit that generates recognition target position information indicating a position on a map of the recognition target from the machine position at the time when the captured image is acquired and the recognition output data is provided.
A harvester in which the estimation probability of the perceptible object is reduced as the recognition object is located farther from the imaging unit in the photographed image. It is a harvester that harvests crops while traveling in the field.
An aircraft position calculation unit that calculates the aircraft position, which is the map coordinates of the aircraft, based on the positioning data from the satellite positioning module.
A photography unit provided on the aircraft to photograph the field during harvesting work,
When the image data of the photographed images sequentially acquired by the photographing unit is input, the existence area where the recognition object exists in the photographed image is estimated, and the existence area and the existence area are estimated. An image recognition module that outputs recognition output data including the estimated probability of
A recognition target position information generation unit that generates recognition target position information indicating a position on a map of the recognition target from the machine position at the time when the captured image is acquired and the recognition output data is provided.
A plurality of the recognized object position information is stored, and the stored plurality of the recognized object position information is corrected based on the result of the statistical calculation of the estimated probability included in the corresponding recognition output data. Harvesting machine. It is a harvester that harvests crops while traveling in the field.
An aircraft position calculation unit that calculates the aircraft position, which is the map coordinates of the aircraft, based on the positioning data from the satellite positioning module.
A photography unit provided on the aircraft to photograph the field during harvesting work,
When the image data of the photographed images sequentially acquired by the photographing unit is input, the existence area where the recognition object exists in the photographed image is estimated, and the existence area and the existence area are estimated. An image recognition module that outputs recognition output data including the estimated probability of
A recognition target position information generation unit that generates recognition target position information indicating a position on a map of the recognition target from the machine position at the time when the captured image is acquired and the recognition output data is provided.
A data storage unit that temporarily and temporally stores the recognition output data sequentially output from the image recognition module as a recognition output data string, and a data determination unit are provided.
The data determination unit inappropriately recognizes and outputs the recognition output data having the estimation probability lower than a predetermined level as compared with the estimation probability of the recognition output data which has a temporal relationship in the recognition output data string. Harvester to judge as data. The harvester according to any one of claims 1 to 3 , wherein the recognition object is at least one of a person, a fallen culm, a weed, and a ridge.

Images